Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sprngr/rubber-duck --skill duck-riskgit clone --depth 1 https://github.com/sprngr/rubber-duckWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sprngr/rubber-duck/duck-risk)<a href="https://agentmods.dev/skills/sprngr/rubber-duck/duck-risk"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-risk/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sprngr/rubber-duck/duck-risk"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-risk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.00509 |
| Opus 5 | $0.00022 | $0.00254 |
| Sonnet 5 | $0.00009 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
duck-risk scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Risk review 🦆. Break it before users do.
Purpose
Identify highest-impact correctness/reliability/security-adjacent risks and smallest safe mitigations.
Philosophy Guardrails (skill-local)
Inherit shared guardrails from references/GUARDRAILS.md.
Skill-specific delta:
- Risk findings and mitigations only; merge/approval decisions remain with user.
Activation
Use for adversarial review of proposal/change scope.
Method
1. Clarify scope (if missing)
- ask 1-3 targeted clarifying questions when context is incomplete
- state assumptions explicitly when evidence is missing
Required:
- proposal/change scope or runtime path
Optional:
- threat model
- rollback constraints
- compatibility constraints
If threat model/scope is missing, ask one targeted clarifying question.
2. Review for risk
- Inspect trust boundaries and failure classes first.
- Prioritize: security/correctness -> data integrity -> rollback/compat.
- Emit max 3 highest-impact findings.
- Include explicit
Impact+Rollbackin every finding. - Prefer smallest safe mitigation.
- If uncertain assumptions, state assumption in one line and downgrade confidence.
3. Output findings
One line per finding:
<prefix> <path[:line|scope]> — <failure mode>. Impact: <user/data/scope>. Rollback: <blast radius + revert path>. Fix: <smallest safe mitigation>.
Prefixes:
🔴 bug:correctness/security/data-loss🟡 risk:reliability/compat/rollback gap❓ question:missing context blocks judgment
Final line:
totals: <n> findings, <n> questions.
coverage: trust-boundary=<checked|partial|missing>; rollback=<checked|partial|missing>.
Boundaries
- No style/naming nits.
- No simplification/duplication ownership (
duck-simplify). - No final PR-thread formatting ownership (
duck-review).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 81 lines · 44 tokens per session scan A 6012d499a7ac
duck-risk is a skill published in the GitHub repository sprngr/rubber-duck (8 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 509 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".